Image analysis method for sensing moving ball, and sensing device using same

Abstract

The present invention is to provide an image analysis method for sensing moving ball, and sensing device using same significantly improving the speed of image processing by performing image analysis by applying an analysis object area set immediately before each acquired image to the current image according to a method that setting an analysis object area, which is a partial area, without analyzing the entire image in analyzing an image for sensing a moving ball in sports with balls, detecting the ball within the set analysis object area, calculating the physical quantity of the ball movement, and setting another analysis object area to include the position where the ball will appear on the image to be analyzed based on the position of the ball detected on the image being analyzed.

The invention claimed is: 
     
         1 . An image analysis method for sensing moving ball performed by a sensing device, comprising:
 acquiring an image in a field of view of a camera facing a space where a ball moves;   detecting a position of the ball from the acquired image;   setting an analysis object area to include a position where a ball will appear on a next image based on the detected position of the ball; and   detecting the position of the ball within the set analysis object area on the next image of the image used to set the analysis object area,   wherein the detecting the position of the ball within the set analysis object area on the next image includes:   calculating a three-dimensional area of the range in which the ball can move using information preset as a limit physical quantity by which the ball can move at the detected position of the ball; and   setting an area including a part projected from a three-dimensional area of the range in which the ball can move to a surface viewed by the camera as the analysis object area.   
     
     
         2 . The method according to  claim 1 , further comprising:
 setting a new analysis object area to include a position where a ball will appear on a next image based on the position of the ball detected within the analysis object area set on the previous image; and   detecting the position of the ball within the new analysis object area on the next image.   
     
     
         3 . The method according to  claim 1 , wherein a three-dimensional area of the range in which the ball can move is calculated by reflecting information on a change in a relative positional relationship between the moving ball and the camera for each acquired image, and the analysis object area is calculated and set from the calculated three-dimensional area. 
     
     
         4 . The method according to  claim 1 , wherein a change in a relative positional relationship between the moving ball and the camera is calculated in advance, a constant three-dimensional area having a size that includes both the current ball position and the ball position in the next image is preset at any position, and the analysis object area is calculated and set from the constant three-dimensional area based on the ball position for each acquired image. 
     
     
         5 . The method according to  claim 1 , wherein the limit physical quantity that the ball can move is preset for each type of golf club that hits the ball, and
 wherein the calculating the three-dimensional area of the range in which the ball can move includes,   identifying a type of the golf club in which the user hits the ball, and calculating the three-dimensional area of the range in which the ball can move by applying the limit physical quantity according to the identified golf club type.   
     
     
         6 . An image analysis method for sensing moving ball performed by a sensing device, comprising:
 acquiring an image in a field of view of a camera facing a space where a ball moves;   detecting a position of the ball from the acquired image;   setting an analysis object area to include a position where a ball will appear on a next image based on the detected position of the ball; and   detecting the position of the ball within the set analysis object area on the next image of the image used to set the analysis object area,   wherein the acquiring the image by the camera includes acquiring images by each of the plurality of stereoscopic-type cameras interconnected with each other, and   wherein detecting the position of the ball within the set analysis object area on the next image includes:   calculating a three-dimensional area of the range in which the ball can move using information preset as a limit physical quantity by which the ball can move at the detected position of the ball; and   setting each area including a part projected from each three-dimensional area of the range in which the ball can move to the surface viewed by each of the plurality of cameras, as an analysis object area for each camera image.   
     
     
         7 . The method according to  claim 6 , wherein a three-dimensional area of the range in which the ball can move is calculated by reflecting information on a change in a relative positional relationship between the moving ball and the camera for each acquired image, and the analysis object area is calculated and set from the calculated three-dimensional area. 
     
     
         8 . The method according to  claim 6 , wherein a change in a relative positional relationship between the moving ball and the camera is calculated in advance, a constant three-dimensional area having a size that includes both the current ball position and the ball position in the next image is preset at any position, and the analysis object area is calculated and set from the constant three-dimensional area based on the ball position for each acquired image. 
     
     
         9 . The method according to  claim 6 , wherein the limit physical quantity that the ball can move is preset for each type of golf club that hits the ball, and
 wherein the calculating the three-dimensional area of the range in which the ball can move includes,   identifying a type of the golf club in which the user hits the ball, and calculating the three-dimensional area of the range in which the ball can move by applying the limit physical quantity according to the identified golf club type.   
     
     
         10 . A sensing device that senses a moving ball through image analysis of the ball that is hit and moved, comprising:
 a camera device that acquires images in a field of view toward a space where the ball moves; and   a sensing processor that detects a position of the ball from the acquired images, sets an analysis object area to include a position where a ball will appear on a next image based on the detected position of the ball, and by detecting the position of the ball within the set analysis object area on the next image of the image used to set the analysis object area, performs image analysis for sensing the ball only within the set analysis object area for each acquired image,   wherein the sensing processor is configured to calculate a three-dimensional area of the range in which the ball can move by using information preset as a limit physical quantity by which the ball can move at the detected position of the ball, and set an area including a part projected from the three-dimensional area of the range in which the ball can move to a surface viewed by the camera device as the analysis object area.   
     
     
         11 . The device according to  claim 10 , wherein the sensing processor is configured to newly calculate and set the analysis object area for each position of the ball by calculating the three-dimensional area of the range in which the ball can move by reflecting information on a change in a relative positional relationship between the moving ball and the camera for each acquired image. 
     
     
         12 . The device according to  claim 10 , wherein the sensing processor is configured to calculate a change in a relative positional relationship between the moving ball and the camera in advance, set an area of a size that can be used at any position in the field of view of the camera device as the analysis object area, and collectively apply the preset analysis object area to the image to be analyzed.